• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2009년도 춘계학술대회 논문집
• /
• pp.91-98
• /
• 2009

For maintaining railroad, accumulated passing tonnage is a determinant factor of appropriate rail replacement time. Recently, Seoul Metro's rail maintaining system and technology is being improved from previous years, which increasing a standard of rail replacement. Thus, this brings importance of estimating and managing for accumulated passing tonnage. In case of light weighted train such as subway, current method of calculating accumulated passing tonnage has defaults of misrepresenting accumulated passing tonnage data. Because current method is based on the weight of passengers and train., and operation data. In addition, currently there is no mechanical and electronic system that could represent and support the accurate data between heavy and non-heavy traffic area, and accumulated passing tonnage is calculated inaccurately by estimating average value each line. The current method of calculating accumulated passing tonnage misleads to unpredictable data that represent inappropriate rail replacement period, which leads to under or over analyzed replacement period. If accumulated passing tonnage is over estimated, rail replacement leads to waste of budget. Hence, it is necessary to construct reliable actual measurement system to manage rail's life safely and efficiently, and in this study the accumulated passing tonnage measurement device is installed with using rail pad of optical fiber sensors and its effect is analyzed.

• 전기학회논문지P
• /
• 제54권2호
• /
• pp.94-100
• /
• 2005

Abnormal symptoms on operating conditions of power transformer are monitored by a preventive diagnostic system which prevents the sudden power failure in case of quick progress of abnormal situation. The preventive diagnostic system helps plan the proper maintenance method according to the transformer conditions via accumulated data. KEPCO has adopted the preventive diagnostic system at nine of 345kV substations since 1997. Application techniques of the diagnostic sensors were settled, but diagnostic algorithm and practical use of accumulated data are not yet established. To build up the diagnostic algorithm and effective use of the preventive diagnostic system, the reliability of the data which were accumulated in a server computer is very important. This paper describes the data analysis in the server in order to advance the reliability of the accumulated data of the preventive diagnostic system. The principles and data flows of the diagnostic sensors were analyzed, and the data discrepancy between sensors and server were calibrated.

• 대한조선학회논문집
• /
• 제42권5호
• /
• pp.534-541
• /
• 2005

Until now, Korean shipyards have accumulated a great amount of data. But they do not have appropriate tools to utilize the data in practical works. Engineering data contains experts' experience and know-how in its own. It is very useful to extract knowledge or information from the accumulated existing data by using data mining technique This paper treats an evolutionary computation based on genetic programming (GP), which can be one of the components to realize data mining. The paper deals with linear models of GP for the regression or approximation problem when given learning samples are not sufficient. The linear model, which is a function of unknown parameters, is built through extracting all possible base functions from the standard GP tree by utilizing the symbolic processing algorithm. In addition to a standard linear model consisting of mathematic functions, one variant form of a linear model, which can be built using low order Taylor series and can be converted into the standard form of a polynomial, is considered in this paper. The suggested model can be utilized as a designing tool to predict design parameters with small accumulated data.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 춘계학술대회
• /
• pp.131-133
• /
• 2017

과거의 누적된 데이터는 미래를 예측하는데 있어서 기본 데이터를 제공한다. 우연성이론에 근거하여 많은 분야에서의 예측 방법들이 활용되고 있지만, 로또번호의 예측은 우연성이론에 근거하지 않는다. 본 연구에서는 누적된 데이터를 통하여 발생하는 예측력의 변화를 알아보는 방법을 제시하고자 한다.

• 반도체디스플레이기술학회지
• /
• 제18권2호
• /
• pp.73-77
• /
• 2019

Data mining techniques can also be used to increase the efficiency of production in the tax sector, which requires professional skills. As tax-related computerization was carried out, large amounts of data were accumulated, creating a good environment for data mining. In this paper, we have developed a system that can help tax accountant who have existing professional abilities by using data mining techniques on accumulated tax related data. The data mining technique used is random forest and improved by using f1-score. Using the implemented system, data accumulated over two years was learned, showing high accuracy at prediction.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.214-218
• /
• 1999

The aim of our study is to develop new algorism for sea fog detection by using Geostational Meteorological Satellite-5(GMS-5) and suggest the techniques of its continuous detection. So as to detect daytime sea fog/stratus(00UTC, May 10, 1999), visible accumulated histogram method and surface albedo method are used. The characteristic value during daytime showed A(min) > 20％ and DA < 10％ when visble accumulated histogram method was applied. And the sea fog region which detected is of similarity in composite image and surface albedo method. In case of nighttime sea fog(18UTC, May 10, 1999), infrared accumulated histogram method and maximum brightness temperature method are used, respectively. Maximum brightness temperature method(T_max method) detected sea fog better than IR accumulated histogram method. In case of T_max method, when infrared value is larger than T_max, fog is detected, where T_max is an unique value, maximum infrared value in each pixel during one month. Then T_max is beneath 700hpa temperature of GDAPS(Global Data Assimilation and Prediction System). Sea fog region which detected by T_max method was similar to the result of National Oceanic and Atmosheric Administration/Advanced Very High Resolution Radiometer (NOAA/AVHRR) DCD(Dual Channel Difference). But inland visibility and relative humidity didn't always agreed well.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2005년도 춘계 학술발표회 논문집
• /
• pp.317-324
• /
• 2005

Korean shipyards have accumulated a great amount of data. But they do not have appropriate tools to utilize the data in practical works. Engineering data contains experts' experience and know-how In its own. It is very useful to extract knowledge or information from the accumulated existing data by using datamining technique. This paper treats an evolutionary computation method based on genetic programming (GP), which can be one of the components to realize datamining.

• 한국경영과학회지
• /
• 제29권4호
• /
• pp.41-60
• /
• 2004

A stream data is a data set that is accumulated to the data storage from a data source over time continuously. The size of this data set, in many cases. becomes increasingly large over time. To mine information from this massive data. it takes much resource such as storage, memory and time. These unique characteristics of the stream data make it difficult and expensive to use this large size data accumulated over time. Otherwise. if we use only recent or part of a whole data to mine information or pattern. there can be loss of information. which may be useful. To avoid this problem. we suggest a method that efficiently accumulates information. in the form of rule sets. over time. It takes much smaller storage compared to traditional mining methods. These accumulated rule sets are used as prediction models in the future. Based on theories of ensemble approaches. combination of many prediction models. in the form of systematically merged rule sets in this study. is better than one prediction model in performance. This study uses a customer data set that predicts buying power of customers based on their information. This study tests the performance of the suggested method with the data set alone with general prediction methods and compares performances of them.

• 한국초지조사료학회지
• /
• 제7권1호
• /
• pp.37-41
• /
• 1987

The purpose of this study is to clarify the effect of top dressing on the thatch losses in bentgrass (Agrostis palustris). Top dressing materials used were clay loam, sand, zeolite, and sawdust. Data were taken on July 10 ($T_1$), Aug. 7 (($T_2$ ) and Sept. 4 (($T_3$) respectively. The results are summarized as follows: 1. The dry weight of accumulated thatch was significantly different between treatments and dates of survery, and for the interaction of treatment x date of survey. 2. The dry weight of accumulated thatch showed a tendency to decrease as growth progressed in all treatments. (Table 1) The dry weight of accumulated thatch was the smallest at sand but the largest at clay loam in each date of survey. 3. The losses rate of accumulated thatch showed a tendency to slightly increase as affected by top dressing materials. (Table 2) Sand showed a significantly higher losses rate of accumulated thatch than that of other treatments. 4. The dry weight of accumulated thatch showed a significant negative correlation (p<0.01) with the losses rate of accumulated thatch. (Fig. 1) 5. Turf coverage was significant difference between treatments and dates of survey. 6. Turf coverage showed a tendency to increase as growth progressed in all treatments. (Table 3) 7. Turf coverage indicated significant negative correlation (p<0.001) with the dry weight of accumulated thatch. (Fig. 2)

• 지능정보연구
• /
• 제17권4호
• /
• pp.109-130
• /
• 2011

연속발생 데이터는 데이터의 원천으로부터 데이터 저장소로 연속적으로 축적이 되는 데이터를 말한다. 이렇게 축적된 데이터의 크기는 시간이 지남에 따라 점점 커진다. 또한 이러한 대용량 데이터에서 정보를 추출하기 위해서는 저장공간, 시간, 그리고 많은 자원이 필요하다. 이러한 연속발생 데이터의 특성은 시간이 지남에 따라 축적된 대용량 데이터의 이용을 어렵고 고비용이 되게 한다. 만약 정보나 패턴을 추출할 때 누적된 전체 발생 데이터 중에서 최근의 일부만 사용 한다면 적은 일부 표본의 사용의 문제로 인하여 전체 데이터 사용에서 발견될 수 있는 유용한 정보의 유실이 있을 수 있다. 이러한 문제점을 해결하기 위해서 본 연구는 연속발생 데이터를 발생 시점에서 계속 모으기 보다 이러한 발생되는 데이터에서 규칙을 추출하여 효율적으로 지식을 관리하고자 한다. 이 방법은 기존의 방법에 비하여 적은 양의 데이터 저장공간을 필요로 한다. 또한 이렇게 축적된 규칙집합은 미래에 예측을 위해서 언제든 실시간 예측을 할 수 있게 준비가 된다. 여러 예측 모델을 결합시키는 방법인 앙상블 이론에 의하면 본 연구가 제시하는 데로 체계적으로 규칙집합을 시간에 따라 융합시킬 경우 더 나은 예측 성과가 가능하다. 본 연구는 주식시장의 변동성을 예측하기 위하여 주식시장 데이터를 사용하였다. 본 연구는 이 데이터를 이용해 본 연구가 제시하는 방법과 기존의 방법의 예측 정확도를 비교 하였다.